static CMARK_INLINE void outc(cmark_renderer *renderer, cmark_escaping escape,
int32_t c, unsigned char nextc) {
bool needs_escaping = false;
bool follows_digit =
renderer->buffer->size > 0 &&
cmark_isdigit(renderer->buffer->ptr[renderer->buffer->size - 1]);
char encoded[ENCODED_SIZE];
needs_escaping =
c < 0x80 && escape != LITERAL &&
((escape == NORMAL &&
(c < 0x20 ||
c == '*' || c == '_' || c == '[' || c == ']' || c == '#' || c == '<' ||
c == '>' || c == '\\' || c == '`' || c == '!' ||
(c == '&' && cmark_isalpha(nextc)) || (c == '!' && nextc == '[') ||
(renderer->begin_content && (c == '-' || c == '+' || c == '=') &&
// begin_content doesn't get set to false til we've passed digits
// at the beginning of line, so...
!follows_digit) ||
(renderer->begin_content && (c == '.' || c == ')') && follows_digit &&
(nextc == 0 || cmark_isspace(nextc))))) ||
(escape == URL &&
(c == '`' || c == '<' || c == '>' || cmark_isspace(c) || c == '\\' ||
c == ')' || c == '(')) ||
(escape == TITLE &&
(c == '`' || c == '<' || c == '>' || c == '"' || c == '\\')));
if (needs_escaping) {
if (escape == URL && cmark_isspace(c)) {
// use percent encoding for spaces
snprintf(encoded, ENCODED_SIZE, "%%%2X", c);
cmark_strbuf_puts(renderer->buffer, encoded);
renderer->column += 3;
} else if (cmark_ispunct(c)) {
cmark_render_ascii(renderer, "\\");
cmark_render_code_point(renderer, c);
} else { // render as entity
snprintf(encoded, ENCODED_SIZE, "&#%d;", c);
cmark_strbuf_puts(renderer->buffer, encoded);
renderer->column += strlen(encoded);
}
} else {
cmark_render_code_point(renderer, c);
}
}
// Attempts to parse a list item marker (bullet or enumerated).
// On success, returns length of the marker, and populates
// data with the details. On failure, returns 0.
static bufsize_t parse_list_marker(cmark_chunk *input, bufsize_t pos,
cmark_list **dataptr) {
unsigned char c;
bufsize_t startpos;
cmark_list *data;
startpos = pos;
c = peek_at(input, pos);
if (c == '*' || c == '-' || c == '+') {
pos++;
if (!cmark_isspace(peek_at(input, pos))) {
return 0;
}
data = (cmark_list *)calloc(1, sizeof(*data));
if (data == NULL) {
return 0;
} else {
data->marker_offset = 0; // will be adjusted later
data->list_type = CMARK_BULLET_LIST;
data->bullet_char = c;
data->start = 1;
data->delimiter = CMARK_PERIOD_DELIM;
data->tight = false;
}
} else if (cmark_isdigit(c)) {
int start = 0;
int digits = 0;
do {
start = (10 * start) + (peek_at(input, pos) - '0');
pos++;
digits++;
// We limit to 9 digits to avoid overflow,
// assuming max int is 2^31 - 1
// This also seems to be the limit for 'start' in some browsers.
} while (digits < 9 && cmark_isdigit(peek_at(input, pos)));
c = peek_at(input, pos);
if (c == '.' || c == ')') {
pos++;
if (!cmark_isspace(peek_at(input, pos))) {
return 0;
}
data = (cmark_list *)calloc(1, sizeof(*data));
if (data == NULL) {
return 0;
} else {
data->marker_offset = 0; // will be adjusted later
data->list_type = CMARK_ORDERED_LIST;
data->bullet_char = 0;
data->start = start;
data->delimiter = (c == '.' ? CMARK_PERIOD_DELIM : CMARK_PAREN_DELIM);
data->tight = false;
}
} else {
return 0;
}
} else {
return 0;
}
*dataptr = data;
return (pos - startpos);
}
// Attempts to parse a list item marker (bullet or enumerated).
// On success, returns length of the marker, and populates
// data with the details. On failure, returns 0.
static int parse_list_marker(cmark_chunk *input, int pos, cmark_list **dataptr)
{
unsigned char c;
int startpos;
cmark_list *data;
startpos = pos;
c = peek_at(input, pos);
if (c == '*' || c == '-' || c == '+') {
pos++;
if (!cmark_isspace(peek_at(input, pos))) {
return 0;
}
data = (cmark_list *)calloc(1, sizeof(*data));
if(data == NULL) {
return 0;
} else {
data->marker_offset = 0; // will be adjusted later
data->list_type = CMARK_BULLET_LIST;
data->bullet_char = c;
data->start = 1;
data->delimiter = CMARK_PERIOD_DELIM;
data->tight = false;
}
} else if (cmark_isdigit(c)) {
int start = 0;
do {
start = (10 * start) + (peek_at(input, pos) - '0');
pos++;
} while (cmark_isdigit(peek_at(input, pos)));
c = peek_at(input, pos);
if (c == '.' || c == ')') {
pos++;
if (!cmark_isspace(peek_at(input, pos))) {
return 0;
}
data = (cmark_list *)calloc(1, sizeof(*data));
if(data == NULL) {
return 0;
} else {
data->marker_offset = 0; // will be adjusted later
data->list_type = CMARK_ORDERED_LIST;
data->bullet_char = 0;
data->start = start;
data->delimiter = (c == '.' ? CMARK_PERIOD_DELIM : CMARK_PAREN_DELIM);
data->tight = false;
}
} else {
return 0;
}
} else {
return 0;
}
*dataptr = data;
return (pos - startpos);
}
static void S_out(cmark_renderer *renderer, cmark_node *node,
const char *source, bool wrap,
cmark_escaping escape) {
int length = (int)strlen(source);
unsigned char nextc;
int32_t c;
int i = 0;
int last_nonspace;
int len;
cmark_chunk remainder = cmark_chunk_literal("");
int k = renderer->buffer->size - 1;
cmark_syntax_extension *ext = NULL;
cmark_node *n = node;
while (n && !ext) {
ext = n->extension;
if (!ext)
n = n->parent;
}
if (ext && !ext->commonmark_escape_func)
ext = NULL;
wrap = wrap && !renderer->no_linebreaks;
if (renderer->in_tight_list_item && renderer->need_cr > 1) {
renderer->need_cr = 1;
}
while (renderer->need_cr) {
if (k < 0 || renderer->buffer->ptr[k] == '\n') {
k -= 1;
} else {
cmark_strbuf_putc(renderer->buffer, '\n');
if (renderer->need_cr > 1) {
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
}
}
renderer->column = 0;
renderer->begin_line = true;
renderer->begin_content = true;
renderer->need_cr -= 1;
}
while (i < length) {
if (renderer->begin_line) {
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
// note: this assumes prefix is ascii:
renderer->column = renderer->prefix->size;
}
len = cmark_utf8proc_iterate((const uint8_t *)source + i, length - i, &c);
if (len == -1) { // error condition
return; // return without rendering rest of string
}
if (ext && ext->commonmark_escape_func(ext, node, c))
cmark_strbuf_putc(renderer->buffer, '\\');
nextc = source[i + len];
if (c == 32 && wrap) {
if (!renderer->begin_line) {
last_nonspace = renderer->buffer->size;
cmark_strbuf_putc(renderer->buffer, ' ');
renderer->column += 1;
renderer->begin_line = false;
renderer->begin_content = false;
// skip following spaces
while (source[i + 1] == ' ') {
i++;
}
// We don't allow breaks that make a digit the first character
// because this causes problems with commonmark output.
if (!cmark_isdigit(source[i + 1])) {
renderer->last_breakable = last_nonspace;
}
}
} else if (c == 10) {
cmark_strbuf_putc(renderer->buffer, '\n');
renderer->column = 0;
renderer->begin_line = true;
renderer->begin_content = true;
renderer->last_breakable = 0;
} else if (escape == LITERAL) {
cmark_render_code_point(renderer, c);
renderer->begin_line = false;
// we don't set 'begin_content' to false til we've
// finished parsing a digit. Reason: in commonmark
// we need to escape a potential list marker after
// a digit:
renderer->begin_content =
renderer->begin_content && cmark_isdigit((char)c) == 1;
} else {
(renderer->outc)(renderer, node, escape, c, nextc);
renderer->begin_line = false;
renderer->begin_content =
renderer->begin_content && cmark_isdigit((char)c) == 1;
}
// If adding the character went beyond width, look for an
// earlier place where the line could be broken:
if (renderer->width > 0 && renderer->column > renderer->width &&
!renderer->begin_line && renderer->last_breakable > 0) {
// copy from last_breakable to remainder
cmark_chunk_set_cstr(renderer->mem, &remainder,
(char *)renderer->buffer->ptr +
renderer->last_breakable + 1);
// truncate at last_breakable
cmark_strbuf_truncate(renderer->buffer, renderer->last_breakable);
// add newline, prefix, and remainder
cmark_strbuf_putc(renderer->buffer, '\n');
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
cmark_strbuf_put(renderer->buffer, remainder.data, remainder.len);
renderer->column = renderer->prefix->size + remainder.len;
cmark_chunk_free(renderer->mem, &remainder);
renderer->last_breakable = 0;
renderer->begin_line = false;
renderer->begin_content = false;
}
i += len;
}
}
